Application of the Velvet noise and its variant for synthetic speech and singing

• Item type: SIG Technical Reports(1)
• 公開日: 2018-02-13
• タイトル: Application of the Velvet noise and its variant for synthetic speech and singing
• タイトル / 言語: en
• タイトル: Application of the Velvet noise and its variant for synthetic speech and singing
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Wakayama University
• 著者所属(英): en
• 著者所属(英): Wakayama University
• 著者名: Hideki, Kawahara
• 著者名(英): Hideki, Kawahara
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The Velvet noise is a sparse signal which sounds smoother than Gaussian white noise. We propose the direct use of the velvet noise and application of its variant for speech and singing synthesis. An interesting variant uses the symmetry of time and frequency in Fourier transform to design the desired signal. This variant can replace the logarithmic domain pulse model, mixed excitation source signals and, a group delay-manipulated excitation pulse which is the excitation source signal of legacy-STRAIGHT.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The Velvet noise is a sparse signal which sounds smoother than Gaussian white noise. We propose the direct use of the velvet noise and application of its variant for speech and singing synthesis. An interesting variant uses the symmetry of time and frequency in Fourier transform to design the desired signal. This variant can replace the logarithmic domain pulse model, mixed excitation source signals and, a group delay-manipulated excitation pulse which is the excitation source signal of legacy-STRAIGHT.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2018-SLP-120, 号 3, p. 1-5, 発行日 2018-02-13
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会